Neural network-based estimation and compensation of friction for enhanced deep drawing process control

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Neural network-based estimation and compensation of friction for enhanced deep drawing process control. / Thiery, Sebastian; Zein El Abdine, Mazhar; Heger, Jens et al.
Material Forming ESAFORM 2024: The 27th International ESAFORM Conference on Material Forming – ESAFORM 2024 – held in Toulouse (France), at the Pierre Baudis Convention Center between 24-26th April, 2024. Hrsg. / Anna Carla Araujo; Arthur Cantarel; France Chabert; Adrian Korycki; Philippe Olivier; Fabrice Schmidt. Millersville: MaterialsResearchForum LLC, 2024. S. 1462-1471 162 (Materials Research Proceedings; Band 41).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Thiery, S, Zein El Abdine, M, Heger, J & Ben Khalifa, N 2024, Neural network-based estimation and compensation of friction for enhanced deep drawing process control. in AC Araujo, A Cantarel, F Chabert, A Korycki, P Olivier & F Schmidt (Hrsg.), Material Forming ESAFORM 2024: The 27th International ESAFORM Conference on Material Forming – ESAFORM 2024 – held in Toulouse (France), at the Pierre Baudis Convention Center between 24-26th April, 2024., 162, Materials Research Proceedings, Bd. 41, MaterialsResearchForum LLC, Millersville, S. 1462-1471, 27th International ESAFORM Conference on Material Forming - ESAFORM 2024, Toulouse, Frankreich, 24.04.24. https://doi.org/10.21741/9781644903131-162

APA

Thiery, S., Zein El Abdine, M., Heger, J., & Ben Khalifa, N. (2024). Neural network-based estimation and compensation of friction for enhanced deep drawing process control. In A. C. Araujo, A. Cantarel, F. Chabert, A. Korycki, P. Olivier, & F. Schmidt (Hrsg.), Material Forming ESAFORM 2024: The 27th International ESAFORM Conference on Material Forming – ESAFORM 2024 – held in Toulouse (France), at the Pierre Baudis Convention Center between 24-26th April, 2024 (S. 1462-1471). Artikel 162 (Materials Research Proceedings; Band 41). MaterialsResearchForum LLC. https://doi.org/10.21741/9781644903131-162

Vancouver

Thiery S, Zein El Abdine M, Heger J, Ben Khalifa N. Neural network-based estimation and compensation of friction for enhanced deep drawing process control. in Araujo AC, Cantarel A, Chabert F, Korycki A, Olivier P, Schmidt F, Hrsg., Material Forming ESAFORM 2024: The 27th International ESAFORM Conference on Material Forming – ESAFORM 2024 – held in Toulouse (France), at the Pierre Baudis Convention Center between 24-26th April, 2024. Millersville: MaterialsResearchForum LLC. 2024. S. 1462-1471. 162. (Materials Research Proceedings). doi: 10.21741/9781644903131-162

Bibtex

@inbook{f4e2ddf944b246ee9973d79801d783f5,
title = "Neural network-based estimation and compensation of friction for enhanced deep drawing process control",
abstract = "Fluctuating process conditions, such as lubrication, can disturb the production process and lead to faulty components that have cracks or wrinkles. Real-time identification of process parameters can detect deviations in sheet forming operations and enable the process parameters to be adjusted. To increase process robustness, closed-loop control is often used to monitor and influence the material draw-in, which corresponds to the material flow and can be measured by camera systems inside the deep-drawing press. The aim of this work is to develop a control concept that can predict the optimum blank holder force by estimating the coefficient of friction based on the material draw-in of the last stroke. Using a cross-die geometry, it is shown how the material draw-in can be determined experimentally by means of a camera system and numerically by FE simulations. Finally, artificial neural network-based models are trained through simulations and are subsequently tested on a numerical case study in which the coefficient of friction is changed as a disturbance variable and must be compensated for. The widely applicable control concept has the potential to incorporate additional softsensors, for example to determine material properties, and other target variables, such as the punch force, into the optimization algorithm.",
keywords = "Engineering, Deep Drawing, Material Draw-In, predictive modelling, Friction Estimation, closed-loop control, Process Monitoring and Stabilization, Particle Swarm Optimization",
author = "Sebastian Thiery and {Zein El Abdine}, Mazhar and Jens Heger and {Ben Khalifa}, Noomane",
note = "Publisher Copyright: {\textcopyright} 2024, Association of American Publishers. All rights reserved.; 27th International ESAFORM Conference on Material Forming - ESAFORM 2024, ESAFORM 2024 ; Conference date: 24-04-2024 Through 26-04-2024",
year = "2024",
month = may,
day = "15",
doi = "10.21741/9781644903131-162",
language = "English",
isbn = "9781644903131",
series = "Materials Research Proceedings",
publisher = "MaterialsResearchForum LLC",
pages = "1462--1471",
editor = "Araujo, {Anna Carla} and Arthur Cantarel and France Chabert and Adrian Korycki and Philippe Olivier and Fabrice Schmidt",
booktitle = "Material Forming ESAFORM 2024",
address = "United States",
url = "https://esaform24.fr/",

}

RIS

TY - CHAP

T1 - Neural network-based estimation and compensation of friction for enhanced deep drawing process control

AU - Thiery, Sebastian

AU - Zein El Abdine, Mazhar

AU - Heger, Jens

AU - Ben Khalifa, Noomane

N1 - Conference code: 27

PY - 2024/5/15

Y1 - 2024/5/15

N2 - Fluctuating process conditions, such as lubrication, can disturb the production process and lead to faulty components that have cracks or wrinkles. Real-time identification of process parameters can detect deviations in sheet forming operations and enable the process parameters to be adjusted. To increase process robustness, closed-loop control is often used to monitor and influence the material draw-in, which corresponds to the material flow and can be measured by camera systems inside the deep-drawing press. The aim of this work is to develop a control concept that can predict the optimum blank holder force by estimating the coefficient of friction based on the material draw-in of the last stroke. Using a cross-die geometry, it is shown how the material draw-in can be determined experimentally by means of a camera system and numerically by FE simulations. Finally, artificial neural network-based models are trained through simulations and are subsequently tested on a numerical case study in which the coefficient of friction is changed as a disturbance variable and must be compensated for. The widely applicable control concept has the potential to incorporate additional softsensors, for example to determine material properties, and other target variables, such as the punch force, into the optimization algorithm.

AB - Fluctuating process conditions, such as lubrication, can disturb the production process and lead to faulty components that have cracks or wrinkles. Real-time identification of process parameters can detect deviations in sheet forming operations and enable the process parameters to be adjusted. To increase process robustness, closed-loop control is often used to monitor and influence the material draw-in, which corresponds to the material flow and can be measured by camera systems inside the deep-drawing press. The aim of this work is to develop a control concept that can predict the optimum blank holder force by estimating the coefficient of friction based on the material draw-in of the last stroke. Using a cross-die geometry, it is shown how the material draw-in can be determined experimentally by means of a camera system and numerically by FE simulations. Finally, artificial neural network-based models are trained through simulations and are subsequently tested on a numerical case study in which the coefficient of friction is changed as a disturbance variable and must be compensated for. The widely applicable control concept has the potential to incorporate additional softsensors, for example to determine material properties, and other target variables, such as the punch force, into the optimization algorithm.

KW - Engineering

KW - Deep Drawing

KW - Material Draw-In

KW - predictive modelling

KW - Friction Estimation

KW - closed-loop control

KW - Process Monitoring and Stabilization

KW - Particle Swarm Optimization

UR - http://www.scopus.com/inward/record.url?scp=85195938681&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/eddd81b4-a7f7-323f-a16a-77ce83bbfbe3/

U2 - 10.21741/9781644903131-162

DO - 10.21741/9781644903131-162

M3 - Article in conference proceedings

SN - 9781644903131

T3 - Materials Research Proceedings

SP - 1462

EP - 1471

BT - Material Forming ESAFORM 2024

A2 - Araujo, Anna Carla

A2 - Cantarel, Arthur

A2 - Chabert, France

A2 - Korycki, Adrian

A2 - Olivier, Philippe

A2 - Schmidt, Fabrice

PB - MaterialsResearchForum LLC

CY - Millersville

T2 - 27th International ESAFORM Conference on Material Forming - ESAFORM 2024

Y2 - 24 April 2024 through 26 April 2024

ER -

DOI

Zuletzt angesehen

Aktivitäten

  1. Understanding Corruption by Means of Experiments
  2. The Ambiguity of In/Activity in John Knights “The Right to be Lazy”
  3. Contracting for Space - 2009
  4. Strange Signs: Invented Languages from Alienation to Zany
  5. Reading Strategy Programs and their Effects on Teachers’ Instruction and Students’ Comprehension in Secondary Schools
  6. Team Entrepreneurial Network(ing)
  7. Crazy, Classified City Life - Hackfeminist Future-Making Practices between Dystopia and Utopia, Predictability and Possibility
  8. Shifting Regimes of Proof: On the Contested Politics of Identification in Border and Migration Management
  9. Building the virtual stage. Insights from co-creating online theatre events
  10. Künstliche Intelligenz in der Hochschullehre
  11. Contrastivity and the pragmatic variable: Responses to thanks across English as a pluricentric language (Language, Nations, Cultures: Pluricentric Languages in Contest (s), Universität Stockholm)
  12. Teaching Game Studies at DiGRA 2014
  13. Mutual Knowledge Conference
  14. Towards more radical forms of governance for business and human rights: From management practice to management education
  15. International Conference on Road Safety and Simulation 2017
  16. CRISIS-DRIVEN TRANSFORMATION IN ORGANIZATIONS
  17. ‘Cultural Ecosystem’ as tool for researching alternative cultures – potentials, limits and the question of ‘another black box’.
  18. EVA 2004
  19. SOLWODI-Fachtagung 2020
  20. Eliane Gilg
  21. Contrastive Pragmatics: A Cross-Disciplinary Journal (Zeitschrift)
  22. From Compliance to Due Diligence: Opportunities and Tensions in the Development of New Sustainable Supply Chain Governance Regimes
  23. Tragic Differing, Discordant Times: Reiner Schürmann’s Ruins
  24. Towards the Design of Active Pharmaceutical ingredients (APIs) mineralizing readily in the Environment
  25. Reviewer Information and Organization
  26. Space and Organizing Practices: Researching Individual Entrepreneurs in the Creative Industries
  27. Universität Duisburg-Essen (Externe Organisation)
  28. Emma Kunz: Drawing as a tool, Healing as a process
  29. Ein berühmter Lüneburger Nikolaus: Niklas Luhmann
  30. AUGE UM AUGE - ZOLL UM ZOLL?
  31. CREPS-Workshop 2004
  32. Research in the Sociology of Organizations (Fachzeitschrift)